Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 368 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.1286. Min Range: -2.1286

Max Act: 2.1286. Min Act: -0.0000

Data Index: 895419 (C4 (Web Text))

Max Activating Token Index: 160

Text #1

Max Range: 2.1286. Min Range: -2.1286

Max Act: 1.5708. Min Act: -0.0000

Data Index: 1188443 (C4 (Web Text))

Max Activating Token Index: 656

Text #2

Max Range: 2.1286. Min Range: -2.1286

Max Act: 1.5922. Min Act: -0.0000

Data Index: 1447601 (Python Code)

Max Activating Token Index: 791

Text #3

Max Range: 2.1286. Min Range: -2.1286

Max Act: 1.4270. Min Act: -0.0000

Data Index: 303846 (C4 (Web Text))

Max Activating Token Index: 953

Text #4

Max Range: 2.1286. Min Range: -2.1286

Max Act: 1.2720. Min Act: -0.0000

Data Index: 664946 (C4 (Web Text))

Max Activating Token Index: 614

Text #5

Max Range: 2.1286. Min Range: -2.1286

Max Act: 1.3711. Min Act: -0.0000

Data Index: 1406943 (Python Code)

Max Activating Token Index: 961

Text #6

Max Range: 2.1286. Min Range: -2.1286

Max Act: 1.2755. Min Act: -0.0000

Data Index: 1570270 (Python Code)

Max Activating Token Index: 530

Text #7

Max Range: 2.1286. Min Range: -2.1286

Max Act: 1.2395. Min Act: -0.0000

Data Index: 1224543 (C4 (Web Text))

Max Activating Token Index: 404

Text #8

Max Range: 2.1286. Min Range: -2.1286

Max Act: 1.0591. Min Act: -0.0000

Data Index: 685995 (C4 (Web Text))

Max Activating Token Index: 674

Text #9

Max Range: 2.1286. Min Range: -2.1286

Max Act: 1.1219. Min Act: -0.0000

Data Index: 922653 (C4 (Web Text))

Max Activating Token Index: 913

Text #10

Max Range: 2.1286. Min Range: -2.1286

Max Act: 1.1853. Min Act: -0.0000

Data Index: 139186 (C4 (Web Text))

Max Activating Token Index: 656

Text #11

Max Range: 2.1286. Min Range: -2.1286

Max Act: 1.1702. Min Act: -0.0000

Data Index: 1263479 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 2.1286. Min Range: -2.1286

Max Act: 1.1637. Min Act: -0.0000

Data Index: 1116465 (C4 (Web Text))

Max Activating Token Index: 106

Text #13

Max Range: 2.1286. Min Range: -2.1286

Max Act: 1.1397. Min Act: -0.0000

Data Index: 767548 (C4 (Web Text))

Max Activating Token Index: 663

Text #14

Max Range: 2.1286. Min Range: -2.1286

Max Act: 1.0126. Min Act: -0.0000

Data Index: 593005 (C4 (Web Text))

Max Activating Token Index: 20

Text #15

Max Range: 2.1286. Min Range: -2.1286

Max Act: 1.0958. Min Act: -0.0000

Data Index: 749944 (C4 (Web Text))

Max Activating Token Index: 1016

Text #16

Max Range: 2.1286. Min Range: -2.1286

Max Act: 1.0609. Min Act: -0.0000

Data Index: 1077597 (C4 (Web Text))

Max Activating Token Index: 485

Text #17

Max Range: 2.1286. Min Range: -2.1286

Max Act: 1.0270. Min Act: -0.0000

Data Index: 1614505 (Python Code)

Max Activating Token Index: 719

Text #18

Max Range: 2.1286. Min Range: -2.1286

Max Act: 1.0377. Min Act: -0.0000

Data Index: 1553244 (Python Code)

Max Activating Token Index: 547

Text #19

Max Range: 2.1286. Min Range: -2.1286

Max Act: 1.0498. Min Act: -0.0000

Data Index: 371152 (C4 (Web Text))

Max Activating Token Index: 959